Share your thoughts, 1 month free Claude Pro on usSee more

Embodied Instruction Following on EB-ALFRED 1.0 (test)

67.2Success Rate (Avg)

ReAct

Updated 1mo ago

Evaluation Results

Method	Links
ReAct 2026.01		67.2	68	68	70	68	62	65.3	72	66	76.7	63	59.7
ReAct 2026.01		63.2	70	64	72	58	52	67.4	74.3	66.7	76.5	62.8	59
ReAct 2026.01		56.8	64	54	68	46	52	65.1	74	60.3	74	58.3	61.3
WorldMind 2026.01		49.2	50	58	54	42	42	55.7	61	61	58.8	48	49.7
WorldMind 2026.01		48	58	48	56	34	44	54.1	63	52.7	61	41.7	52
SimuRA 2026.01		45.6	52	44	54	38	40	52.2	61	50.3	58.2	45.3	46.3
SimuRA 2026.01		45.2	50	42	54	38	42	53.6	57.8	47.8	59.7	48.5	54.3
ReAct 2026.01		44.4	52	48	52	32	38	50.4	55.3	53.5	55.3	42.7	45
BoN 2026.01		44.4	46	44	50	42	40	49.5	50.8	48.3	54.7	48.7	45
BoN 2026.01		42.8	46	42	50	42	34	50.4	54.2	46.5	56.5	52	42.8
ReasoningBank 2026.01		41.6	50	36	44	36	42	47.6	57.5	41.5	47	44.2	48
ReAct 2026.01		41.2	50	40	46	38	32	47.5	55.3	42.8	52.2	47.2	39.8
AWM 2026.01		41.2	44	36	48	38	40	46	48.3	42	52.5	44.3	42.7
AWM 2026.01		40	46	32	48	40	34	46.2	53.2	39.2	50.7	47	41
Synapse 2026.01		38.8	38	46	40	36	34	43.6	42.5	51.3	42.7	42	39.7
ReasoningBank 2026.01		38	42	36	42	34	36	42.6	46.7	38.8	45.8	41.5	40.3
Synapse 2026.01		37.2	40	32	44	36	34	42.2	41.2	37.5	49.5	41.3	41.7
ReAct 2026.01		37	41	40	39	16	49	41	42.3	35.3	43.3	35.7	40.3
ReAct 2026.01		35.2	38	34	44	28	32	37.6	43.7	37.3	49.2	35.3	36
ReAct 2026.01		28.8	34	28	36	24	22	34.3	47.8	35.3	43.5	33.3	29